paper-with-me

Papers

Multi-Target Backdoor Attacks Against Speaker Recognition

2025-08-12 · Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak, Patrick Cardinal arxiv

In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditions, we vary the signal-to-noise ratio between speech and trigger, demonstrating a trade-off between stealth and effectiveness. We further extend the attack to the speaker verification task by selecting the most similar training speaker - based on cosine similarity - as a proxy target. The attack is most effective when target and enrolled speaker pairs are highly similar, reaching success rates of up to 90% in such cases.

📄 PDF Abstract BibTeX arXiv:2508.08559

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker IdentificationSpeaker VerificationSpeaker Recognition

Similar Papers 제목 키워드 기반

MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems

2023-09-13 · Hanqing Guo, Xun Chen, Junfeng Guo, Li Xiao 외

Speaker Verification (SV) is widely deployed in mobile systems to authenticate legitimate users by using their voice traits. In this work, we propose a backdoor attack MASTERKEY, to compromise the SV models. Different fr…

Backdoor AttackSpeaker Verification

Backdoor Attack against Speaker Verification

2020-10-22 · Tongqing Zhai, Yiming Li, Ziqi Zhang, Baoyuan Wu 외

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to …

Backdoor AttackClusteringSpeaker VerificationUser Identification

CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks

2025-06-20 · Yinghao Wu, Liyan Zhang

Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated…

Backdoor Attackbackdoor defense

One-to-N & N-to-One: Two Advanced Backdoor Attacks Against Deep Learning Models

2022-05-01 · IEEE Transactions on Dependable and Secure Computing 2022 5 · Mingfu Xue, Can He, Jian Wang, and Weiqiang Liu

—In recent years, deep learning models have been widely deployed in various application scenarios. The training processes of deep neural network (DNN) models are time-consuming, and require massive training data and lar…

Face Recognition

BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models

2020-10-06 · Ahmed Salem, Yannick Sautter, Michael Backes, Mathias Humbert 외

The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption …

Backdoor AttackBIG-bench Machine LearningFraud Detection